Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование
Classification of Hyperspectral Images with Different Methods of Training Set Formation. / Borzov, S. M.; Potaturkin, O. I.
в: Optoelectronics, Instrumentation and Data Processing, Том 54, № 1, 01.01.2018, стр. 76-82.Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование
}
TY - JOUR
T1 - Classification of Hyperspectral Images with Different Methods of Training Set Formation
AU - Borzov, S. M.
AU - Potaturkin, O. I.
PY - 2018/1/1
Y1 - 2018/1/1
N2 - The efficiency of the methods of controlled spectral and spectral-spatial classification of vegetation types on the basis of hyperspectral pictures with different methods of training set formation is evaluated. The dependence of the classification accuracy on the number of spectral features is considered. It is shown that simultaneous allowance for spatial and spectral features ensures highquality classification of similarly looking types of vegetation by merely using training sets with the maximum degree of the pixel distribution over the image.
AB - The efficiency of the methods of controlled spectral and spectral-spatial classification of vegetation types on the basis of hyperspectral pictures with different methods of training set formation is evaluated. The dependence of the classification accuracy on the number of spectral features is considered. It is shown that simultaneous allowance for spatial and spectral features ensures highquality classification of similarly looking types of vegetation by merely using training sets with the maximum degree of the pixel distribution over the image.
KW - classification of surface types
KW - hyperspectral image
KW - remote sensing
KW - spectral and spatial features
UR - http://www.scopus.com/inward/record.url?scp=85044840104&partnerID=8YFLogxK
U2 - 10.3103/S8756699018010120
DO - 10.3103/S8756699018010120
M3 - Article
AN - SCOPUS:85044840104
VL - 54
SP - 76
EP - 82
JO - Optoelectronics, Instrumentation and Data Processing
JF - Optoelectronics, Instrumentation and Data Processing
SN - 8756-6990
IS - 1
ER -
ID: 12475493